Subsymbolic Natural Language Processing

The self-organizing map (SOM) is an automatic data-analysis method. It is widely applied to clustering problems and data exploration in industry, finance, natural sciences, and linguistics.

MIIKKULAINEN, Risto, 1993. Subsymbolic natural language processing: an integrated model of scripts, lexicon, and memory. Cambridge, Mass: MIT Press. Neural network modeling and connectionism. ISBN 978-0-262-13290-9.

Recently there has been a lot of excitement in Cognitive Science about the subsymbolic (i.e. Parallel Distributed Processing, or distributed connectionist, or distributed neural network) approach. Subsymbolic systems seem to capture a number of intriguing properties of human­ like information processing such as Learning From Examples, context sensitivity, generalization, robustness of behavior, and intuitive reason­ing. These properties have been very difficult to model with traditional, symbolic techniques.

Within this new paradigm, the central issues are quite different (even incompatible) from the traditional issues in symbolic cognitive science, and the research has proceeded without much in common with the past. However, the ultimate goal is still the same: to understand how human cognition is put together. Even if cognitive science is being built on a new foundation, as can be argued, many of the results obtained through symbolic research are still valid, and could be used as a guide­ line for developing subsymbolic models of cognitive processes.

This is where DISCERN, the computer-simulated neural network model described in this book, fits in. DISCERN is built purely on paral­lel distributed mechanisms, but at the high level it consists of modules and information structures similar to those of symbolic systems, such as Scripts, Lexicon, and Episodic Memory. At the highest level of cog­nitive modeling, the symbolic and subsymbolic paradigms have to ad­dress the same basic issues. Outlining a parallel distributed approach to those issues is the purpose of this book. DISCERN is, above all, a prototype of a subsymbolic natural language processing system.